The traveling-wave ultrasonic motor (TWUM) drive offers many distinct advantages but suffers from severe system nonlinearities and parameter variations, especially during speed control. This paper presents a new speed tracking control system for the TWUM drive, which newly incorporates neuro-fuzzy control and direct pulsewidth modulation to solve the problem of nonlinearities and variations. The proposed control system is digitally implemented by a low-cost digital-signal-processor-based microcontroller, hence reducing the system hardware size and cost. Experimental results confirm that the proposed speed tracking controller can offer good steady-state and transient performance.

With their significant advantages over traditional electromagnetic motors, ultrasonic motors (USMs) are becoiming attractive. This paper presents a neuro-fuzzy dualmode controller, combining the knowledge-based fuzzy logic and the leaming-incorporated neural network as well as using dual control inputs, for servo control of travelling-wave USMk. According to the proposed neuro-fuzzy control, both the driving frequency and phase difference of the USM system are simultaneously on-line adjusted. Experimental results have verified its superior steady-state and dynamic perfalrmances under various reference inputs.